works on

From the 1 of 11 linked papers with an AI index.

activity
20242026
collaborators

11 papers

cs.CV2026

Beyond Visual Ambiguity: Guiding Robust Monocular Depth Estimation in Challenging Scenarios via Detailed Long Captions

Junrui Zhang, Jiaqi Li, Yiran Wang +2

The paper introduces CapDepth, a framework that uses detailed long textual captions to guide monocular depth estimation, improving robustness on non‑Lambertian surfaces and in adve…

cs.CV2026

Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization

Liao Shen, Wentao Jiang, Yiran Zhu +4

Recent advances in image-to-video (I2V) generation have achieved remarkable progress in synthesizing high-quality, temporally coherent videos from static images. Among all the appl…

cs.CV2025

BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching

Yachuan Huang, Xianrui Luo, Qiwen Wang +6

Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approac…

cs.CV2025

Generative Photographic Control for Scene-Consistent Video Cinematic Editing

Huiqiang Sun, Liao Shen, Zhan Peng +9

Cinematic storytelling is profoundly shaped by the artful manipulation of photographic elements such as depth of field and exposure. These effects are crucial in conveying mood and…

cs.CV2025

MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction

Yaopeng Lou, Liao Shen, Tianqi Liu +4

We present Multi-Baseline Gaussian Splatting (MuGS), a generalized feed-forward approach for novel view synthesis that effectively handles diverse baseline settings, including spar…

cs.CV2025

Dynamic View Synthesis from Small Camera Motion Videos

Huiqiang Sun, Xingyi Li, Juewen Peng +4

Novel view synthesis for dynamic D scenes poses a significant challenge. Many notable efforts use NeRF-based approaches to address this task and yield impressive results. Howeve…