arXiv (All)
open access
Frozen History: When Temporal Losses Stop Accumulation in Learned Real-Time Supersampling
Learned real-time supersampling accumulates jittered low-resolution samples along motion vectors. Many methods use a temporal consistency loss to reduce flicker. We show that with accurate registration, this loss can suppress accumulation: on static content, the network copies its warped history at
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Replay in the Silent Degrees of Freedom: Continual Learning Without an Offline Phase#1115586
- High-Throughput Generative Video Super-Resolution on a Single Consumer GPU#1297531
- SAGA: Stable Acceleration Guidance for Autoregressive Video Generation#1155260
- Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher#1248759
- Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History#1142410
Record · ID 1327002
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive