# Human-level 3D shape perception emerges from multi-view learning

arXiv: https://arxiv.org/abs/2602.17650 · HTML: https://mlsanity.com/paper/2602.17650/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [Block-Recurrent Dynamics in Vision Transformers](https://mlsanity.com/paper/2512.19941/) (2025)
- [Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriously](https://mlsanity.com/paper/2104.01490/) (2021)
- [The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences](https://mlsanity.com/paper/2406.10447/) (2024)
- [Evaluating Multiview Object Consistency in Humans and Image Models](https://mlsanity.com/paper/2409.05862/) (2024)
- [Approaching human 3D shape perception with neurally mappable models](https://mlsanity.com/paper/2308.11300/) (2023)
- [A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments](https://mlsanity.com/paper/2512.13517/) (2025)

## Built on by (most cited first, 2 of 2)

- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [QualiaNet: An Experience-Before-Inference Network](https://mlsanity.com/paper/2604.14193/) (2026)

## Abstract (arXiv)

Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods have fallen short of human performance. Here we develop a modeling framework that predicts human 3D shape inferences for arbitrary objects, directly from experimental stimuli. We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data; given a set of images taken from different locations within a natural scene, these models learn to predict spatial information related to these images, such as camera location and visual depth, without relying on any object-related inductive biases. Notably, these visual-spatial signals are analogous to sensory cues readily available to humans. We design a zero-shot evaluation approach to determine the performance of these 'multi-view' models on a well established 3D perception task, then compare model and human behavior. Our modeling framework is the first to match human accuracy on 3D shape inferences, even without task-specific training or fine-tuning. Remarkably, independent readouts of model responses predict fine-grained measures of human behavior, including error patterns and reaction times, revealing a natural correspondence between model dynamics and human perception. Taken together, our findings indicate that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data. Code, images, and human data needed to reproduce all analyses can be found at https://tzler.github.io/human_multiview/