arXiv cs.GR details PriMoRetarget, a motion-retargeting framework that uses explicit priority levels instead of fragile weight tuning. For game teams building humanoid animation pipelines, the pitch is better preservation of …
Nicholas Ioannidis, Dun Yang, Max Smith, Tue Vu, Ziyu Zhang, Shayegan Omidshafiei, Xue Bin Peng·
arXiv cs.GR details Sonic-AMG, a streaming system for generating human motion from spatial audio in real time. The model separates sound content from source geometry, then uses causal motion generation …
ACM Graphics details a new time-integration method for elastodynamic contact that lets simulation energy be controlled more directly. For game teams wrestling with soft-body stability, this points toward fewer explosive …
ACM Graphics details HIL, a hybrid imitation learning approach for dynamic athletic control that targets more responsive character motion. The work sits in ACM Transactions on Graphics 46(2) and points …
Jiashun WangYifeng JiangHaotian ZhangChen TesslerDavis RempeJessica HodginsXue Bin Peng·
ACM Graphics details RCPG, a real-time product path guiding technique built on radiance cascades. The work targets faster light transport sampling for interactive rendering, with a publication date of April …
arXiv cs.GR details ResLRB, a differentiable light tracing method that keeps peak memory constant even as path length and sensor connections grow. For graphics programmers, the key trick is stochastic …
arXiv cs.GR details Tabula Rasa, a Monte Carlo method for generating unit-variance noise with controlled spatio-temporal correlation. The technique targets temporal coherence in graphics pipelines and claims simpler, faster code …
Tobias Ritschel, Yang Zhou, Nick Milef, Mikhail Dereviannykh, Chen Liu, Christophe Hery, Carl Marshall·
arXiv cs.GR details a new attribution method for diffusion models that tracks how training examples shape generation over time, not just which samples matter. CADT builds counterfactual response trajectories across …
USC Institute for Creative Technologies says a 10-second look at a caregiver-support virtual human splits reactions by AI experience. Newcomers worry whether they can use it; experienced users question whether …
arXiv cs.GR details a kinetic theory for self-evolving LLM agents, framing gated skill rewrites as a population process. The paper argues that validation gates, plugin interactions, and density changes can …
arXiv cs.GR details a wildfire-monitoring VLM that turns 2D simulations into labeled video episodes, then uses them as memory for training-free reporting. The system hit 51.5% exact four-tag accuracy on …
Duowen Chen, Yuchen Sun, Zhiqi Li, Yuxuan Liao, Sinan Wang, Bart van Bloemen Waanders, Bo Zhu·
arXiv cs.GR details SoftPaint, a zero-shot diffusion editing method that gives image and video tools pixel-level control with soft masks. Instead of all-or-nothing masking, it lets creators dial edit strength …
arXiv cs.GR details a modal kinetic typography system that animates vector letters from their own vibration modes while keeping them readable. The method uses a finite-element eigenproblem plus a frozen …
arXiv cs.GR details a design tool that can rapidly test whether 3D obstacle-course layouts are solvable under designer-set constraints. It pairs GPU-accelerated simulation with search and RL guidance, giving level …
SIGGRAPH announced its 2026 award winners, spotlighting standout work across art, animation, emerging tech, immersive experiences, real-time graphics, and research. For developers, the list is a useful snapshot of where …
arXiv cs.GR details CuACD, a fully GPU-resident approximate convex decomposition pipeline that turns triangle meshes into convex parts much faster. The authors say it can cut preprocessing from tens of …
arXiv cs.GR details OREO, a 3D generation alignment method that uses on-the-fly edited renderings to push models toward more realistic assets. The system feeds refined 2D views back as pseudo-targets, …
Zhiyuan Ma, Wenbo Hu, Wang Zhao, Pengfei Wang, Ying Shan, Lei Zhang·
3d generationai assetsdiffusion modelscomputer graphicsresearch
SIGGRAPH has unveiled the keynote lineup for SIGGRAPH Asia 2026, putting Markus Gross, Ran Huang, and Andrea Vedaldi on stage. For graphics programmers and technical artists, that usually signals a …
SIGGRAPH says Don Greenberg, 92, headlined the Pioneers featured talk in a hybrid session at SIGGRAPH 2026, putting a long-view spotlight on one of computer graphics' early figures. For developers, …
ACM SIGGRAPH·
siggraphcomputer graphicshistoryresearchtechnical art
arXiv cs.GR details VideoX-Qwen, a data-centric video editing pipeline that pairs instruction data with a unified editor. The system builds 1.2 million directional edit records and reports strong results against …
JJiahang Li, Dingbao Shao, Xinyu Chen, Song Wu, Jiang Lin, Duo Li, Yuhang Liu, Jiaxin Hu, Shengrong Gu, Ying Tai, Zili Yi·
aivideo editinggraphicscinematicsresearch
Page 1 of 6
Advertisement
Beta Feedback
With your permission, GameDev.net uses analytics cookies to understand how people use the platform.
You can accept analytics or continue with necessary cookies only.
Learn more