arXiv:2605.16981v3 Announce Type: replace Abstract: Streaming 3D reconstruction under a strict constant-memory budget hinges on how the recurrent state is updated as the stream evolves. We profile TT...
arXiv:2609.36929v1 Announce Type: new Abstract: Recent event-based depth estimation methods successfully transfer geometric priors from vision foundation models via cross-modal distillation. However,...
arXiv:2609.25803v1 Announce Type: new Abstract: High-rate dense perception in dynamic environments is limited by the low update rate of RGB cameras, as rapid scene changes can occur between frames. E...
Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set of context views and process them jointly. This limits their applicability to online scenarios where calibrated views arrive sequentially and the scene must be updated causally.
arXiv:2601. 22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data.
arXiv:2512. 02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions.
arXiv:2609.15032v1 Announce Type: new Abstract: Live free-viewpoint visualization of real humans is critical for immersive communication and interactive digital experiences. Existing methods either r...
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.
World in World introduces a training‑free, inference‑time interface that transforms diverse control signals—such as source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual states. These states are processed by a frozen causal video model’s self‑attention, enabling tasks like camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer without additional training. The method employs a correspondence router and evidence‑wise attention to align token identities and regulate auxiliary channel contributions during a single denoising pass.
arXiv:2608.20788v1 Announce Type: new Abstract: Deep learning-based Multi-View Stereo (MVS) has advanced significantly but often generalizes poorly to unseen scenes, particularly in occluded areas or...
arXiv:2607.02554v2 Announce Type: replace Abstract: Sparse-view neural reconstruction in outdoor driving is challenging due to narrow forward-facing trajectories and limited multi-view overlap, and m...
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.