NVIDIA Researchers Introduce Déjà View for 3D Reconstruction from Photos
Understand the event
NVIDIA researchers introduced Déjà View, a 117-million-parameter model that reconstructs 3D geometry and camera positions from photos taken at different angles. The researchers said it matched or outperformed models up to ten times larger on five benchmarks while using comparable or less compute. Déjà View loops a single transformer block, and researchers can adjust the number of loops to fit their compute budget. NVIDIA presented the work as a NeurIPS 2026 oral paper and shared its code.
Generated by AI from reports · Updated 5 days ago
Read next
More changes in today’s briefingGemini Connects to Google Wallet for Personal Finance InsightsReport timeline
Follow the reports to explore different sides of the event.
- Asian Governments Respond to Jensen Huang’s Departure from Nvidia
Asian governments have responded to Jensen Huang’s departure from Nvidia by reaffirming chip supply plans, monitoring local projects and continuing investigations. South Korea said Nvidia had reaffirmed plans to supply 260,000 advanced GPUs and continue joint AI projects. Singapore said its investigation into Megaspeed and six other people remains ongoing.
- Meet Déjà View, a model that turns photos taken from different angles into 3D geometry and camera positions. By looping a single transformer block, this 117M-parameter model matches or outperforms models up to 10x larger across five benchmarks, using comparable or less compute. Researchers can dial the number of loops to fit their compute budget. #NeurIPS2026 oral paper + code: http://research.nvidia.com/labs/dvl/projects/dvlt
Meet Déjà View, a model that turns photos taken from different angles into 3D geometry and camera positions. By looping a single transformer block, this 117M-parameter model matches or outperforms models up to 10x larger across five benchmarks, using comparable or less compute. Researchers can dial the number of loops to fit their compute budget. #NeurIPS2026 oral paper + code: research.nvidia.com/labs/dvl/…
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue
Event heat trend
- Current within comparable coverage
- 3
- Peak within comparable coverage
- 1011/12 06:00 (UTC+8)
- 24-hour change
- -51%
Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.