-
Class imbalance: what SynBalance shows
SynBalance (ICCV Workshops 2025) adds generated images for rare classes. On ImageNet-LT, accuracy on the rarest classes rises from 12.6% to 21.4%.
-
Synthetic humans: from SURREAL to BEDLAM
From SURREAL (6.5M frames) to BEDLAM, Michael Black’s line of work shows when synthetic humans match real data, when they don’t, and what’s missing.
-
ROSE: removing objects in video with 3D data
ROSE removes objects from video along with their shadows and reflections, trained on 16,678 rendered 3D pairs. See the numbers and what they don’t prove.
-
DAViD from Microsoft: vision trained on synthetic only
Microsoft’s DAViD trains depth, normals and masks for people on 300K synthetic images. See the numbers, where it trails Sapiens-2B, and the limits.
-
AI and the brain: what the MIT study actually shows
MIT’s EEG study of 54 people writing with and without ChatGPT found weaker connectivity and poorer recall of the text. It doesn’t show brain damage.
-
Ghost AI: what we know about Builder.ai and Amazon
The “ghost AI” story: what the press reported about Builder.ai and Amazon’s checkout, what was disputed, and what it teaches about transparency in AI.
-
Geo4D: 4D reconstruction trained only on synthetic
Geo4D (ICCV 2025) reconstructs 4D scenes from monocular video, trained only on synthetic data. See the numbers on real video and where it struggles.
-
Big tech and synthetic data: what the evidence says
Nvidia, Google and OpenAI all talk about synthetic data. What each source says, what is announcement and what is result, and what it means for vision.
// field_notes
Blog: synthetic data and computer vision
De experimentos a insights — histórias reais sobre dados sintéticos e IA.From experiments to insights — real stories on synthetic data and AI.
ArquivoArchive
CategoriasCategories
Posts recentesRecent Posts
TagsTags
4D reconstruction AI and the brain AI ethics AI infrastructure AI transparency BEDLAM bias ChatGPT class imbalance computer vision dataset augmentation depth fundamentals generative models ghost AI Infinigen introduction long-tail recognition MIT study monocular video object removal opinion paper analysis pre-training procedural generation quality inspection real-data limit representation learning representativeness robotics semantic segmentation sim-to-real SMPL SURREAL synthetic data synthetic humans synthetic images tech giants video
