computer vision · 23 topics

sensenova u1 5

marigold v2 revisiting diffusion transformers for monocular depth estimation

drivezero end to end driving beyond human demonstrations

holocount holistic visual counting benchmark mllms

mass multiplayer world models

refertrack embodied visual tracking

diffusion seed pruning

mt editflow

self calibrating cross camera homography mct

small ai models let drones autonomously identify and attack battlefield targets

apple taming outlier tokens in diffusion transformers

gh esd grounded hypothesis driven error slice discovery

show me examples inferring visual concepts from image sets

one layer is enough adapting pretrained visual encoders

incentivizing temporal awareness in egocentric video understanding models

dvd jepa world model

apple pico image codec

us government uap documents

automatically redact pii in images with amazon nova

stanford gpic dataset

rgb normalization 255 vs 256

seashell morphology analysis

simplisafe video doorbell series 2