Joung, Sunghun Kim, Seungryong Kim, Minsu Kim, Ig-Jae Sohn, Kwanghoon 2024-01-12T04:08:41Z 2024-01-12T04:08:41Z 2022-07-15 2021-10 https://pubs.kist.re.kr/handle/201004/77784 We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D annotation. We accomplish this by representing an object as a composition of 3D shape and its appearance, while eliminating the effect of camera viewpoint, in a canonical configuration. Unlike conventional methods modeling spatial variation in 2D images only, our method is capable of reconfiguring the appearance feature in a canonical 3D space, thus enabling the subsequent object classifier to be invariant under 3D geometric variation. Our representation also allows us to go beyond existing methods, by incorporating 3D shape variation as an additional cue for object recognition. To learn the model without ground-truth 3D annotation, we deploy a differentiable renderer in an analysis-by-synthesis framework. By incorporating 3D shape and appearance jointly in a deep representation, our method learns the discriminative representation of the object and achieves competitive performance on fine-grained image recognition and vehicle re-identification. We also demonstrate that the performance of 3D shape reconstruction is improved by learning fine-grained shape deformation in a boosting manner. English IEEE Learning Canonical 3D Object Representation for Fine-Grained Recognition Conference 10.1109/ICCV48922.2021.00107 1 18th IEEE/CVF International Conference on Computer Vision (ICCV), pp.1015 - 1025 18th IEEE/CVF International Conference on Computer Vision (ICCV) 1015 1025 US ELECTR NETWORK 2021-10-11 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) 000797698901020