UGG unifies video generation and 4D geometric prediction
One model treats RGB, depth, and camera pose as conditional completion and can search scene hypotheses at inference.
Stories per day · 30 days
Relatedcamera-pose2video-generation24d-perception14d-scenes1computer-vision1generative-models1lora1monocular-depth1point-tracking1self-supervised-learning1
7 stories, newest first · one card per story
Stories tagged #depth-estimation
MaSS makes self-supervised monocular depth scale across mixed scenes
A decoupled structure pathway lets mixed-domain training help, with zero-shot tests on eight more datasets.
Gen4P: Video Generators are 4D Perceivers
Gen4P turns a pretrained video generator into a single-pass 4D perceiver for tracking, depth, and pose.
Pumpire: Unified Benchmark for Metric Distance Estimation
Pumpire benchmarks point-pair metric distance accuracy for image and video 3D foundation models.
speridlabs/iris-3b — new model trending #30 on Hugging Face
Sperid Labs released Iris-3B, a 3-billion-parameter pixel-space image model that also does depth and upscaling.
7
Illusion of Depth: Revealing Hidden Stereo Vision Vulnerabilities in Depth Estimation
Simple repeating patterns let attackers shift stereo-camera depth estimates by up to 20 meters, triggering emergency braking in autonomous driving frameworks at 40 km/h.
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Marigold V2 adapts diffusion transformers for monocular depth estimation, improving AbsRel 16-26% over the previous best on KITTI and ETH3D.