Computer Vision
Research on Computer Vision: explanations, evidence, limitations and connections between papers.
11 results
Video compression cuts generation time while preserving Wan2.1 scores
In Wan2.1 tests, GRACE uses fewer video tokens while keeping generated-video quality scores near the uncompressed model.
Two adapters let audio–video generation stream in a few steps
A parallel adapter method combines streaming and few-step audio–video generation, matching a bidirectional system’s image quality in held-out tests.
Patch-level visual learning scales with a simpler objective
JEM aligns image patches across views and performs strongly in frozen-feature tests, especially on dense visual tasks.
Evoke uses bounded scene memory for long-video sessions
Evoke combines bounded scene recall with long-horizon training; tests show a specific brightness-stability gain, not universal consistency.
TopoGPU streams image topology calculations through GPUs
TopoGPU speeds image-based persistent homology against CRipser, while CPU memory limits some very large cases.
One model learns faster image generation and understanding
A two-stage method cuts decoding steps while improving image and captioning results for a discrete multimodal model.
A world model checks whether GUI actions lead as expected
LGWM checks GUI transitions by comparing predicted and observed screens, and distinguishes harmful from benign mismatches in tested cases.
Motion fakes leave clues MoDA uses to detect and trace
MoDA combines visual meaning and fine detail to detect motion deepfakes, including clips from two unseen video platforms.
A rule for splitting images can preserve object-finding recall
A theory and overlapping-view rule explain when splitting large images can preserve object-finding recall under stated conditions.
A reviewed MRI workflow finds duplicate identities across datasets
HAPPEN combines exact scan matching and human review, finding cross-dataset duplicates in an audited MRI repository.
TouchScale pairs 500 hours of human video with touch
A 500-hour visual-and-touch dataset improves contact prediction and robot task success in the tested settings.