TL;DR
This paper introduces the first VLM-based depth completion framework, with almost no architectural modifications, that extends the capability of VLM toward 3D perception through three key aspects: visual tok-enization, textual prompt, and textual supervision.
CapDepth is proposed, a novel framework for robust MDE that leverages guidance from detailed long captions to alleviate visual ambiguities in both challenging scenarios, and which outperforms state-of-the-art methods.
Qwen-3D is introduced, a geometry-aware LMM that compresses visual information within the Qwen backbone using multi-view geometric cues, enabling efficient long-horizon visual reasoning over static scenes and incorporates a query-based segmentation decoder that grounds language directly in the underlying 3D scene repre...
This work introduces \method, a Multi-scale Adaptive Vision Encoder, a Multi-scale Adaptive Vision Encoder that uses position-dependent gates to fuse shallow, intermediate, and deep features from a vision Transformer, preserving global semantics while enhancing edges, text, and local structure.
The AP-LCA approach introduces a novel local cross-modal alignment strategy that utilizes image cropping and similarity-based semantic contribution assessment to precisely map fine-grained descriptions to relevant local image regions.
A detection-guided dynamic attention steering system that leverages the locality insight from CNNs to efficiently steer a VLM’s attention toward more relevant sections of an image and demonstrates the effectiveness of combining different model architectures to harness their respective strengths for advancing VLM capabi...
A VLM-native framework that detects cross-frame object correspondence and explicitly models object presence states, thereby enabling accurate and consistent visual grounding under streaming inputs, and introduces Streaming Grounding Reinforcement (SGR), which optimizes TempoGround with verifiable Grounding, Identity, a...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
