Combining a difficulty-balancing loss with an occlusion-avoiding loss yields modest but consistent accuracy gains on optical flow and stereo depth benchmarks.
Liteflownet3: Resolv- ing correspondence ambiguity for more accurate optical flow estimation
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
background 1representative citing papers
citing papers explorer
-
Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties
Combining a difficulty-balancing loss with an occlusion-avoiding loss yields modest but consistent accuracy gains on optical flow and stereo depth benchmarks.