Explicit instance decomposition with per-class shared weights improves latent-transformer video prediction in the paper's experiments, but the claimed advantage is weakened by mismatched parameter counts and test-set temperature selection.
Learning Semantic-Aware Dynamics for Video Prediction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose an architecture and training scheme to predict video frames by explicitly modeling dis-occlusions and capturing the evolution of semantically consistent regions in the video. The scene layout (semantic map) and motion (optical flow) are decomposed into layers, which are predicted and fused with their context to generate future layouts and motions. The appearance of the scene is warped from past frames using the predicted motion in co-visible regions; dis-occluded regions are synthesized with content-aware inpainting utilizing the predicted scene layout. The result is a predictive model that explicitly represents objects and learns their class-specific motion, which we evaluate on video prediction benchmarks.
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
On the Benefits of Instance Decomposition in Video Prediction Models
Explicit instance decomposition with per-class shared weights improves latent-transformer video prediction in the paper's experiments, but the claimed advantage is weakened by mismatched parameter counts and test-set temperature selection.