3 papers
cs.RO2026
OccPlanner: Goal-Aware Occupancy-Conditioned Diffusion Planner for Pixel-Goal Navigation
Binling Huang, Nianjin Ye, Xi Yang +6
Pixel-goal navigation specifies targets directly in the agent's camera view, but a target pixel provides neither metric depth nor traversability, making 3D goal grounding and colli…
cs.CV2026
Rethinking Text-Based Image Retrieval in Specific Domain
Jingyang Tan, Sheng Yang, Yuanpeng Chen +4
Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress. However, existing benchmarks are predominan…
cs.CV2026
LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency
Weilong Yan, Haipeng Li, Hao Xu +4
This paper introduces LaS-Comp, a zero-shot and category-agnostic approach that leverages the rich geometric priors of 3D foundation models to enable 3D shape completion across div…