cs.GR

arXiv:2503.22605v1 Announce Type: new Abstract: Talking head synthesis has become a key research area in computer graphics and multimedia, yet most existing methods often struggle to balance generation quality with computational efficiency. In this paper, we present a novel approach that leverages an Audio Factorization Plane (Audio-Plane) based Gaussian Splatting for high-quality and real-time talking head generation. For modeling a dynamic talking head, 4D volume representation is needed. However, directly storing a dense 4D grid is impractical due to the high cost and lack of scalability for longer durations. We overcome this challenge with the proposed Audio-Plane, where the 4D volume representation is decomposed into audio-independent space planes and audio-dependent planes. This provides a compact and interpretable feature representation for talking head, facilitating more precise audio-aware spatial encoding and enhanced audio-driven lip dynamic modeling. To further improve speech dynamics, we develop a dynamic splatting method that helps the network more effectively focus on modeling the dynamics of the mouth region. Extensive experiments demonstrate that by integrating these innovations with the powerful Gaussian Splatting, our method is capable of synthesizing highly realistic talking videos in real time while ensuring precise audio-lip synchronization. Synthesized results are available in https://sstzal.github.io/Audio-Plane/.

arXiv:2503.21931v1 Announce Type: new Abstract: Problems in differentiable rendering often involve optimizing scene parameters that cause motion in image space. The gradients for such parameters tend to be sparse, leading to poor convergence. While existing methods address this sparsity through proxy gradients such as topological derivatives or lagrangian derivatives, they make simplifying assumptions about rendering. Multi-resolution image pyramids offer an alternative approach but prove unreliable in practice. We introduce a method that uses locally orderless images, where each pixel maps to a histogram of intensities that preserves local variations in appearance. Using an inverse rendering objective that minimizes histogram distance, our method extends support for sparsely defined image gradients and recovers optimal parameters. We validate our method on various inverse problems using both synthetic and real data.

arXiv:2503.22236v1 Announce Type: new Abstract: With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sharp estimation; (2) a normal-to-geometry learning approach that uses normal-regularized latent diffusion learning to enhance 3D geometry generation fidelity; and (3) a 3D data synthesis pipeline that constructs a high-quality dataset to support training. Extensive experiments demonstrate the effectiveness and superiority of our framework in generating rich geometric details, outperforming state-of-the-art methods in terms of fidelity. Our work provides a new direction for high-fidelity 3D geometry generation from images by leveraging normal maps as an intermediate representation.

arXiv:2412.03889v2 Announce Type: replace Abstract: For designing a wide range of everyday objects, the design process should be aware of both the human body and the underlying semantics of the design specification. However, these two objectives present significant challenges to the current AI-based designing tools. In this work, we present a method to synthesize body-aware 3D objects from a base mesh given an input body geometry and either text or image as guidance. The generated objects can be simulated on virtual characters, or fabricated for real-world use. We propose to use a mesh deformation procedure that optimizes for both semantic alignment as well as contact and penetration losses. Using our method, users can generate both virtual or real-world objects from text, image, or sketch, without the need for manual artist intervention. We present both qualitative and quantitative results on various object categories, demonstrating the effectiveness of our approach.

arXiv:2503.21847v1 Announce Type: new Abstract: We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech. The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture to explicitly model co-speech motion dynamics. This architecture enables joint spatial-temporal dependency modeling, thereby enhancing gesture naturalness and fidelity through coherent motion synthesis. To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization, thereby improving the naturalness and fluency of zero-shot motion generation for unseen speech inputs. To mitigate inherent limitations of autoregressive inference, including error accumulation and limited self-correction, we propose an iterative reconstruction inference (IRI) strategy. IRI refines motion sequences via cyclic pose reconstruction, driven by two key components: (1) classifier-free guidance improves distribution alignment between generated and real gestures without auxiliary supervision, and (2) a temporal smoothing process eliminates abrupt inter-frame transitions while ensuring kinematic continuity. Extensive experiments on benchmark datasets validate ReCoM's effectiveness, achieving state-of-the-art performance across metrics. Notably, it reduces the Fr\'echet Gesture Distance (FGD) from 18.70 to 2.48, demonstrating an 86.7% improvement in motion realism. Our project page is https://yong-xie-xy.github.io/ReCoM/.

arXiv:2503.21816v1 Announce Type: new Abstract: Gaussian Splatting (GS)-based methods rely on sufficient training view coverage and perform synthesis on interpolated views. In this work, we tackle the more challenging and underexplored Extrapolated View Synthesis (EVS) task. Here we enable GS-based models trained with limited view coverage to generalize well to extrapolated views. To achieve our goal, we propose a view augmentation framework to guide training through a coarse-to-fine process. At the coarse stage, we reduce rendering artifacts due to insufficient view coverage by introducing a regularization strategy at both appearance and geometry levels. At the fine stage, we generate reliable view priors to provide further training guidance. To this end, we incorporate an occlusion awareness into the view prior generation process, and refine the view priors with the aid of coarse stage output. We call our framework Enhanced View Prior Guidance for Splatting (EVPGS). To comprehensively evaluate EVPGS on the EVS task, we collect a real-world dataset called Merchandise3D dedicated to the EVS scenario. Experiments on three datasets including both real and synthetic demonstrate EVPGS achieves state-of-the-art performance, while improving synthesis quality at extrapolated views for GS-based methods both qualitatively and quantitatively. We will make our code, dataset, and models public.

arXiv:2503.21886v1 Announce Type: new Abstract: High-fidelity reconstruction of head avatars from monocular videos is highly desirable for virtual human applications, but it remains a challenge in the fields of computer graphics and computer vision. In this paper, we propose a two-phase head avatar reconstruction network that incorporates a refined 3D mesh representation. Our approach, in contrast to existing methods that rely on coarse template-based 3D representations derived from 3DMM, aims to learn a refined mesh representation suitable for a NeRF that captures complex facial nuances. In the first phase, we train 3DMM-stored NeRF with an initial mesh to utilize geometric priors and integrate observations across frames using a consistent set of latent codes. In the second phase, we leverage a novel mesh refinement procedure based on an SDF constructed from the density field of the initial NeRF. To mitigate the typical noise in the NeRF density field without compromising the features of the 3DMM, we employ Laplace smoothing on the displacement field. Subsequently, we apply a second-phase training with these refined meshes, directing the learning process of the network towards capturing intricate facial details. Our experiments demonstrate that our method further enhances the NeRF rendering based on the initial mesh and achieves performance superior to state-of-the-art methods in reconstructing high-fidelity head avatars with such input.

arXiv:2503.22159v1 Announce Type: new Abstract: Novel-view synthesis (NVS) for dynamic scenes from 2D images presents significant challenges due to the spatial complexity and temporal variability of such scenes. Recently, inspired by the remarkable success of NVS using 3D Gaussian Splatting (3DGS), researchers have sought to extend 3D Gaussian models to four dimensions (4D) for dynamic novel-view synthesis. However, methods based on 4D rotation and scaling introduce spatiotemporal deformation into the 4D covariance matrix, necessitating the slicing of 4D Gaussians into 3D Gaussians. This process increases redundant computations as timestamps change-an inherent characteristic of dynamic scene rendering. Additionally, performing calculations on a four-dimensional matrix is computationally intensive. In this paper, we introduce Disentangled 4D Gaussian Splatting (Disentangled4DGS), a novel representation and rendering approach that disentangles temporal and spatial deformations, thereby eliminating the reliance on 4D matrix computations. We extend the 3DGS rendering process to 4D, enabling the projection of temporal and spatial deformations into dynamic 2D Gaussians in ray space. Consequently, our method facilitates faster dynamic scene synthesis. Moreover, it reduces storage requirements by at least 4.5\% due to our efficient presentation method. Our approach achieves an unprecedented average rendering speed of 343 FPS at a resolution of $1352\times1014$ on an RTX 3090 GPU, with experiments across multiple benchmarks demonstrating its competitive performance in both monocular and multi-view scenarios.

arXiv:2408.15270v2 Announce Type: replace Abstract: Traditional reinforcement learning methods for human-object interaction (HOI) rely on labor-intensive, manually designed skill rewards that do not generalize well across different interactions. We introduce SkillMimic, a unified data-driven framework that fundamentally changes how agents learn interaction skills by eliminating the need for skill-specific rewards. Our key insight is that a unified HOI imitation reward can effectively capture the essence of diverse interaction patterns from HOI datasets. This enables SkillMimic to learn a single policy that not only masters multiple interaction skills but also facilitates skill transitions, with both diversity and generalization improving as the HOI dataset grows. For evaluation, we collect and introduce two basketball datasets containing approximately 35 minutes of diverse basketball skills. Extensive experiments show that SkillMimic successfully masters a wide range of basketball skills including stylistic variations in dribbling, layup, and shooting. Moreover, these learned skills can be effectively composed by a high-level controller to accomplish complex and long-horizon tasks such as consecutive scoring, opening new possibilities for scalable and generalizable interaction skill learning. Project page: https://ingrid789.github.io/SkillMimic/

arXiv:2411.17067v2 Announce Type: replace Abstract: Geometric reconstruction of opaque surfaces from images is a longstanding challenge in computer vision, with renewed interest from volumetric view synthesis algorithms using radiance fields. We leverage the geometry field proposed in recent work for stochastic opaque surfaces, which can then be converted to volume densities. We adapt Gaussian kernels or surfels to splat the geometry field rather than the volume, enabling precise reconstruction of opaque solids. Our first contribution is to derive an efficient and almost exact differentiable rendering algorithm for geometry fields parameterized by Gaussian surfels, while removing current approximations involving Taylor series and no self-attenuation. Next, we address the discontinuous loss landscape when surfels cluster near geometry, showing how to guarantee that the rendered color is a continuous function of the colors of the kernels, irrespective of ordering. Finally, we use latent representations with spherical harmonics encoded reflection vectors rather than spherical harmonics encoded colors to better address specular surfaces. We demonstrate significant improvement in the quality of reconstructed 3D surfaces on widely-used datasets.

arXiv:2503.21991v1 Announce Type: new Abstract: In this paper, we tackle the copy-paste image-to-image composition problem with a focus on object placement learning. Prior methods have leveraged generative models to reduce the reliance for dense supervision. However, this often limits their capacity to model complex data distributions. Alternatively, transformer networks with a sparse contrastive loss have been explored, but their over-relaxed regularization often leads to imprecise object placement. We introduce BOOTPLACE, a novel paradigm that formulates object placement as a placement-by-detection problem. Our approach begins by identifying suitable regions of interest for object placement. This is achieved by training a specialized detection transformer on object-subtracted backgrounds, enhanced with multi-object supervisions. It then semantically associates each target compositing object with detected regions based on their complementary characteristics. Through a boostrapped training approach applied to randomly object-subtracted images, our model enforces meaningful placements through extensive paired data augmentation. Experimental results on established benchmarks demonstrate BOOTPLACE's superior performance in object repositioning, markedly surpassing state-of-the-art baselines on Cityscapes and OPA datasets with notable improvements in IOU scores. Additional ablation studies further showcase the compositionality and generalizability of our approach, supported by user study evaluations.

arXiv:2411.18665v2 Announce Type: replace Abstract: Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based renderers, these neural rendering engines are limited by the lack of manual control over the lighting, which is often essential for improving or personalizing the desired image outcome. In this paper, we show that precise lighting control can be achieved for object relighting simply by providing a coarse shadow of the object. Indeed, we show that injecting only the desired shadow of the object into a pre-trained diffusion-based neural renderer enables it to accurately shade the object according to the desired light position, while properly harmonizing the object (and its shadow) within the target background image. Our method, SpotLight, leverages existing neural rendering approaches and achieves controllable relighting results with no additional training. We show that SpotLight achieves superior object compositing results, both quantitatively and perceptually, as confirmed by a user study, outperforming existing diffusion-based models specifically designed for relighting. We also demonstrate other applications, such as hand-scribbling shadows and full-image relighting, demonstrating its versatility.

arXiv:2501.08552v2 Announce Type: replace Abstract: Procedural Content Generation (PCG) is widely used to create scalable and diverse environments in games. However, existing methods, such as the Wave Function Collapse (WFC) algorithm, are often limited to static scenarios and lack the adaptability required for dynamic, narrative-driven applications, particularly in augmented reality (AR) games. This paper presents a reinforcement learning-enhanced WFC framework designed for mobile AR environments. By integrating environment-specific rules and dynamic tile weight adjustments informed by reinforcement learning (RL), the proposed method generates maps that are both contextually coherent and responsive to gameplay needs. Comparative evaluations and user studies demonstrate that the framework achieves superior map quality and delivers immersive experiences, making it well-suited for narrative-driven AR games. Additionally, the method holds promise for broader applications in education, simulation training, and immersive extended reality (XR) experiences, where dynamic and adaptive environments are critical.

arXiv:2412.00733v4 Announce Type: replace Abstract: Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintenance, audio conditioning, and video extrapolation inapplicable. To address this limitation, we design an identity reference network consisting of a causal 3D VAE combined with a stacked series of transformer layers, ensuring consistent facial identity across video sequences. Additionally, we investigate various speech audio conditioning and motion frame mechanisms to enable the generation of continuous video driven by speech audio. Our method is validated through experiments on benchmark and newly proposed wild datasets, demonstrating substantial improvements over prior methods in generating realistic portraits characterized by diverse orientations within dynamic and immersive scenes. Further visualizations and the source code are available at: https://fudan-generative-vision.github.io/hallo3/.

arXiv:2503.09630v1 Announce Type: new Abstract: Diffusion models have transformed image generation, yet controlling their outputs for diverse applications, including content moderation and creative customization, remains challenging. Existing approaches usually require task-specific training and struggle to generalize across both concrete (e.g., objects) and abstract (e.g., styles) concepts. We propose CASteer (Cross-Attention Steering) a training-free framework for controllable image generation using steering vectors to influence a diffusion model$'$s hidden representations dynamically. CASteer computes these vectors offline by averaging activations from concept-specific generated images, then applies them during inference via a dynamic heuristic that activates modifications only when necessary, removing concepts from affected images or adding them to unaffected ones. This approach enables precise control over a wide range of tasks, including removing harmful content, adding desired attributes, replacing objects, or altering styles, all without model retraining. CASteer handles both concrete and abstract concepts, outperforming state-of-the-art techniques across multiple diffusion models while preserving unrelated content and minimizing unintended effects.

arXiv:2503.10031v1 Announce Type: new Abstract: How does AI connect to the past in conservation? What can 17 years old photos be helpful in a renewed effort of preservation? This research aims to use AI to connect both in a seamless 3D reconstruction of heritage from imagery data taken from Gongfan Palace, Yunlin Taiwan. AI-assisted 3D modeling was used to reconstruct correspondent details across different 3D platforms of 3DGS or NeRF models generated by Postshot or KIRI Engine. Polygon or point models by Zephyr were referred to and assessed in two sets. The results also include AI-assist modeling outcomes in Stable Diffusion and Postshot-based animation. The evolved documenta-tion and interpretation in AI presents a novel arrangement of working processes contributed by new structure and management of resources, formats, and interfaces, as a continuous preservation effort.

arXiv:2411.16816v3 Announce Type: replace Abstract: Ensuring the safety of autonomous robots, such as self-driving vehicles, requires extensive testing across diverse driving scenarios. Simulation is a key ingredient for conducting such testing in a cost-effective and scalable way. Neural rendering methods have gained popularity, as they can build simulation environments from collected logs in a data-driven manner. However, existing neural radiance field (NeRF) methods for sensor-realistic rendering of camera and lidar data suffer from low rendering speeds, limiting their applicability for large-scale testing. While 3D Gaussian Splatting (3DGS) enables real-time rendering, current methods are limited to camera data and are unable to render lidar data essential for autonomous driving. To address these limitations, we propose SplatAD, the first 3DGS-based method for realistic, real-time rendering of dynamic scenes for both camera and lidar data. SplatAD accurately models key sensor-specific phenomena such as rolling shutter effects, lidar intensity, and lidar ray dropouts, using purpose-built algorithms to optimize rendering efficiency. Evaluation across three autonomous driving datasets demonstrates that SplatAD achieves state-of-the-art rendering quality with up to +2 PSNR for NVS and +3 PSNR for reconstruction while increasing rendering speed over NeRF-based methods by an order of magnitude. See https://research.zenseact.com/publications/splatad/ for our project page.

arXiv:2503.08061v2 Announce Type: replace Abstract: Realistic hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on a kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact forces and finger torques. Consequently, these approaches prioritize tight, one-size-fits-all grips rather than reflecting users' intended force levels. We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions, faithfully reflecting the user's grip force intention. Instead of mimicking predefined motion datasets, ForceGrip uses generated training scenarios-randomizing object shapes, wrist movements, and trigger input flows-to challenge the agent with a broad spectrum of physical interactions. To effectively learn from these complex tasks, we employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization. This progressive strategy ensures stable hand-object contact, adaptive force control based on user inputs, and robust handling under dynamic conditions. Additionally, a proximity reward function enhances natural finger motions and accelerates training convergence. Quantitative and qualitative evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods. The video presentation of our paper is accessible at https://youtu.be/lR-YAfninJw.

arXiv:2503.09642v1 Announce Type: new Abstract: Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this report, we present Open-Sora 2.0, a commercial-level video generation model trained for only $200k. With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. We detail all techniques that contribute to this efficiency breakthrough, including data curation, model architecture, training strategy, and system optimization. According to human evaluation results and VBench scores, Open-Sora 2.0 is comparable to global leading video generation models including the open-source HunyuanVideo and the closed-source Runway Gen-3 Alpha. By making Open-Sora 2.0 fully open-source, we aim to democratize access to advanced video generation technology, fostering broader innovation and creativity in content creation. All resources are publicly available at: https://github.com/hpcaitech/Open-Sora.

arXiv:2503.09641v1 Announce Type: new Abstract: This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pre-trained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving state-of-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step - outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10x faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024 x 1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.