5 papers
World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models
Junyi Wu, Zekun Li, Chenhongyi Yang +9
Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual memory: the previously obse…
From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models
Feiran Wang, Xiaoqi Wang, Ziwei Li +3
Predicting future spatial states supports collision avoidance and timely decision-making in dynamic environments. However, existing vision-language models (VLMs) and benchmarks for…
LIST3R: Long-sequence Instance-aware 3D Reconstruction
Jing Gao, Wei Wang, Feiran Wang +1
We present LIST3R, an instance-aware framework for long-sequence 3D reconstruction inspired by the way humans organize spatial memory around stable and recognizable objects. LIST3R…
Consistent Instance Field for Dynamic Scene Understanding
Junyi Wu, Van Nguyen Nguyen, Benjamin Planche +11
We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding. Unlike prior methods that rely on discrete tr…
From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields
Jiachen Tao, Benjamin Planche, Van Nguyen Nguyen +13
Accurately modeling light transport is essential for realistic image synthesis. Photon mapping provides physically grounded estimates of complex global illumination effects such as…