Vista4D: Video Reshooting with 4D Point Clouds, CVPR 2026 Highlight
rsasaki0109 · x · 2026-08-14
Vista4D is a video reshooting framework that synthesizes dynamic scenes from novel camera trajectories and viewpoints. It bridges the distribution shift between training and inference for point-cloud-grounded video reshooting by training on noisy, reconstructed multiview videos, making it robust to point cloud artifacts. Its 4D point cloud with temporally-persistent static points preserves scene content and improves camera control. It generalizes to dynamic scene expansion, 4D scene recomposition, and long video inference.
More from Research
- NVIDIA's ProtoMotions: GPU-Accelerated Simulation Framework for Humanoids — carlosdponx · 2026-08-14
- Demystifying Stable Diffusion: A Deep Dive into the Orchestrator Layer — Mahmoud_Zalt · 2026-08-14
- CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation — ebenworks · 2026-08-14
- Solving Agent Self-Destruction in RSI: A Paradigm for Spatiotemporal Composability — philipvollet · 2026-08-14
- Hackathon Alert: Build Custom LLM Benchmarks for Real-World Scenarios — 葬AI · 2026-08-14
- Duke, Meta, and Princeton introduce PAHF for adaptive AI agents — burkov · 2026-08-14