CV researchers ask: is computer vision 'mostly done' in the age of large models?
CSProfKGD · x · 2026-09-14
- Michael Black, heading to ECCV 2026, reflects on academic CV research's role as large models grow. His paper VIGA is the first agentic approach to inverse graphics, turning a single image into a 3D Blender scene; its first version was rejected, delaying publication significantly.
- The quoted thread argues CV must expand into every science/engineering domain with visual data (robotics and medical imaging today, potentially 100x more fields later) or narrow CV — image/video/3D understanding and reconstruction — will become 'mostly done' like signal processing and NLP before it.
- The author notes seeing physics, chemistry, and physiology researchers at last year's CVPR, hoping the conference becomes an all-science festival as CV moves outward into other disciplines.
More from AGI Musings
- Nina Schick: public distrusts regulators as much as AI labs — nobody can 'pace' AI — NinaDSchick · 2026-09-14
- Jensen Huang: next 2 decades of progress may exceed all of history combined — rohanpaul_ai · 2026-09-14
- Researcher: I'm less worried about AI x-risk than in 2022 — time to retire p(doom) — soumitrashukla9 · 2026-09-14
- Security veteran to AI labs: capability isn't risk, cyber evals lack real-world threat modeling — HackingLZ · 2026-09-14
- GPT-4o psychosis snippets eerily resemble SCP wiki stories, likely in training data — code_star · 2026-09-14
- Vals AI: frontier labs shouldn't grade their own frontier; models may match researchers by Aug 2027 — JenniferHli · 2026-09-14