Graphics

Davis Rempe, Mathis Petrovich, Ye Yuan et al.

This addresses the need for scalable, high-quality human motion data for applications in robotics, simulation, and entertainment, representing a significant advancement over previous limited datasets.

Junxuan Li, Rawal Khirodkar, Chengan He et al.

This work addresses the problem of creating realistic and generalizable 3D avatars for applications in virtual reality, gaming, and digital humans, representing a novel approach rather than an incremental improvement.

Ahmed H. Mahmoud, Rahul Goel, Jonathan Ragan-Kelley et al.

It provides a practical solution for researchers and engineers needing efficient derivatives for mesh-based optimization problems, with demonstrated performance gains.

Yuanhang Lei, Tao Cheng, Xingxuan Li et al.

This addresses a fundamental problem in computer graphics for animators and developers by providing a generalizable and efficient solution for physics-based animation.

Hao Liu, Yuxuan Lin, Jingfeng Guo et al.

For 3D content creators needing precise local editing of assets, VS3D provides a novel approach that avoids the limitations of external masking and multi-view lifting.

Aviad Dahan, Moran Yanuka, Noa Kraicer et al. · apple-ml

It addresses the challenge of synchronizing personalized audio with video for content creators, offering a novel integrated approach rather than incremental improvements.

Yuxuan Bian, Zeyue Xue, Songchun Zhang et al.

This work addresses the fundamental memory bottleneck in infinite video generation, offering a practical path toward real-time, unbounded-length video synthesis for content creation and simulation applications.

Haozhe Chi, Jinghan Li, Hao Jiang et al.

This work addresses token redundancy in image tokenization for generative models, offering a more efficient and scalable paradigm.

Zeyu Cai, Yuliang Xiu, Renke Wang et al.

For researchers and practitioners in 3D human modeling, OmniFit solves the practical problem of scale ambiguity in AI-generated assets and multi-modal inputs, enabling robust body fitting without metric scale.

Ryan Po, David Junhao Zhang, Amir Hertz et al.

This work addresses the lack of user control and shared inference in video world models, enabling editable and multiplayer experiences for game developers and interactive simulation users.

Runjie Yan, Yan-Pei Cao, Peng Wang et al.

This work addresses the problem of scalable generative 3D modeling by bridging adaptive rendering primitives with generative models, offering a new representation that improves quality and stability for single-image-to-3D generation.

Jaskirat Singh, Boyang Zheng, Zongze Wu et al.

This work provides a practical, training-efficient improvement for generative modeling with diffusion transformers, relevant to researchers in image and video generation.

Jon Hasselgren, Zheng Zeng, Milos Hasan et al.

This addresses the problem of efficient material generation for 3D content creators, though it appears incremental as it builds on existing diffusion and VAE techniques.

Dilin Wang, Xiaoyu Xiang, Kihyuk Sohn et al.

It addresses the need for fast, deployable 3D asset generation for interactive workflows, particularly in gaming and AR/VR, where user experience and real-time performance are critical.

Ruixiang Jiang, Chang Wen Chen

This work addresses the unexplored problem of pre-capture computational planning for portrait photography, offering a novel approach for photographers and computer graphics practitioners.

Leyi Qi, Yiming Li, Siyuan Liang et al.

For developers of large-scale T2I models, this addresses the vulnerability of existing watermarking methods to adversarial removal, providing a provably robust verification solution.

Chuanrui Zhang, Minghan Qin, Yuang Wang et al.

This addresses the gap in creating sim-ready interactive objects for embodied AI and physical simulation, representing a novel method rather than an incremental improvement.

Weiyu Li, Antoine Toisoul, Tom Monnier et al.

This work addresses the scalability and quantization issues in mesh generation for 3D content creators, offering a significant speedup over existing approaches.

Tingwu Wang, Olivier Dionne, Michael De Ruyter et al.

It bridges the gap between generative motion research and industry production by enabling scalable real-time motion control with intuitive authoring, applicable to animation and humanoid robotics.

Xin Zhang, Yabo Chen, Yijie Fang et al.

For researchers in generative video and 3D scene generation, TelePhysics addresses the lack of physical consistency and controllability in existing methods, offering a training-free solution.