depth map
PulseAugur coverage of depth map — every cluster mentioning depth map across labs, papers, and developer communities, ranked by signal.
-
New DART pretraining method enhances surgical vision models with depth data
Researchers have developed DART, a new pretraining method for surgical vision foundation models that incorporates depth map information alongside standard RGB images. This approach, which builds upon the DINOv2 architec…
-
New VisTa3D dataset targets thin object 3D reconstruction challenges
Researchers have introduced VisTa3D, a novel dataset and benchmark designed to improve the 3D reconstruction of thin objects. Current 3D reconstruction models struggle with thin objects due to their limited visual and p…
-
MixDiffusion framework enables multi-condition text-to-image synthesis
Researchers have introduced MixDiffusion, a novel framework designed to enhance text-to-image generation by allowing the integration of multiple control conditions simultaneously. Unlike existing methods that are typica…
-
ProxyPose uses video-to-video translation for 6-DoF pose tracking
Researchers have developed ProxyPose, a novel method for tracking the six-degree-of-freedom (6-DoF) pose of objects and surfaces from monocular video. This approach reframes the problem as a video-to-video translation t…
-
SpatialSV framework enhances MLLMs' 3D spatial awareness with interpretable visual supervision
Researchers have introduced SpatialSV, a novel framework aimed at enhancing the 3D spatial awareness of multimodal large language models (MLLMs). Unlike existing methods that rely on external tools or opaque feature dis…
-
New frameworks tackle open-vocabulary 3D scene graph generation
Two new research papers introduce novel frameworks for generating open-vocabulary 3D scene graphs. The first, RelWitness, addresses incomplete supervision by using visual-geometric cues to verify relations between objec…