DidSee is a diffusion-based depth completion model that combines a zero terminal-SNR noise scheduler, single-step training, and a semantic segmentation enhancer to achieve state-of-the-art results on non-Lambertian objects.
Fine-tuning image-conditional diffusion models is easier than you think
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DidSee: Diffusion-Based Depth Completion for Material-Agnostic Robotic Perception and Manipulation
DidSee is a diffusion-based depth completion model that combines a zero terminal-SNR noise scheduler, single-step training, and a semantic segmentation enhancer to achieve state-of-the-art results on non-Lambertian objects.