Multimodal language models (MLLMs) are increasingly being applied in real-world environments, necessitating their ability to interpret 3D spaces and comprehend temporal dynamics. Current methods often rely on specialized architectural designs or task-specific fine-tuning to achieve this. We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs’ spatial-temporal reasoning with 2D images as input, without modifying the architecture or requiring task-specific fine-tuning. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints, and then conveys this information to MLLMs through visual prompting. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks that require spatial-temporal reasoning, including +20.5% improvement on ScanQA, +9.7% on OpenEQA’s episodic memory subset, +6.0% on the long-form video benchmark EgoSchema, and +11% on the R2R navigation benchmark. Additionally, we show that Coarse Correspondences can also enhance open-source MLLMs’ spatial reasoning (by +6.9% on ScanQA) when applied in both training and inference and that the improvement can generalize to unseen datasets such as SQA3D (+3.1%). Taken together, we show that Coarse Correspondences effectively and efficiently boosts models’ performance on downstream tasks requiring spatial-temporal reasoning.

Recent advances in generative imagery have brought forth outpainting and inpainting models that can produce high-quality, plausible image content in unknown regions. However, the content these models hallucinate is necessarily inauthentic, since they are unaware of the true scene. In this work, we propose RealFill, a novel generative approach for image completion that fills in missing regions of an image with the content that should have been there. RealFill is a generative inpainting model that is personalized using only a few reference images of a scene. These reference images do not have to be aligned with the target image, and can be taken with drastically varying viewpoints, lighting conditions, camera apertures, or image styles. Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene. We evaluate RealFill on a new image completion benchmark that covers a set of diverse and challenging scenarios, and find that it outperforms existing approaches by a large margin. Project page: https://realfill.github.io.

DreamFusion [31] has recently demonstrated the utility of a pretrained text-to-image diffusion model to optimize Neural Radiance Fields (NeRF) [23], achieving remarkable text-to-3D synthesis results. However, the method has two inherent limitations: (a) extremely slow optimization of NeRF and (b) low-resolution image space supervision on NeRF, leading to low-quality 3D models with a long processing time. In this paper, we address these limitations by utilizing a two-stage optimization framework. First, we obtain a coarse model using a low-resolution diffusion prior and accelerate with a sparse 3D hash grid structure. Using the coarse representation as the initialization, we further optimize a textured 3D mesh model with an efficient differentiable renderer interacting with a high-resolution latent diffusion model. Our method, dubbed Magic3D, can create high quality 3D mesh models in 40 minutes, which is 2× faster than DreamFusion (reportedly taking 1.5 hours on average), while also achieving higher resolution. User studies show 61.7% raters to prefer our approach over DreamFusion. Together with the image-conditioned generation capabilities, we provide users with new ways to control 3D synthesis, opening up new avenues to various creative applications.

Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images. Without any additional fine-tuning or supervision on the task-specific data or annotations, DIFT is able to outperform both weakly-supervised methods and competitive off-the-shelf features in identifying semantic, geometric, and temporal correspondences. Particularly for semantic correspondence, DIFT from Stable Diffusion is able to outperform DINO and OpenCLIP by 19 and 14 accuracy points respectively on the challenging SPair-71k benchmark. It even outperforms the state-of-the-art supervised methods on 9 out of 18 categories while remaining on par for the overall performance. Project page: https://diffusionfeatures.github.io.

In this paper we reformulate few-shot classification as a reconstruction problem in latent space. The ability of the network to reconstruct a query feature map from support features of a given class predicts membership of the query in that class. We introduce a novel mechanism for few-shot classification by regressing directly from support features to query features in closed form, without introducing any new modules or large-scale learnable parameters. The resulting Feature Map Reconstruction Networks are both more performant and computationally efficient than previous approaches. We demonstrate consistent and substantial accuracy gains on four fine-grained benchmarks with varying neural architectures. Our model is also competitive on the non-fine-grained mini-ImageNet and tiered-ImageNet benchmarks with minimal bells and whistles.1

Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree of invariance to pose, articulation and background. A solution is to use pose-normalized representations: first localize semantic parts in each image, and then describe images by characterizing the appearance of each part. While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification. With a minimal increase in model capacity, pose normalization improves accuracy between 10 and 20 percentage points for shallow and deep architectures, generalizes better to new domains, and is effective for multiple few-shot algorithms and network backbones. Code is available at https://github.com/Tsingularity/PoseNorm_Fewshot.

Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities. The availability of rich contextual information requires a nimble learning scheme that tightly integrates with deep neural networks and has the ability to capture correlation structures among exponentially many outcomes. We propose MEDL_CVAE, which encodes a conditional multivariate distribution as a generating process. As a result, the variational lower bound of the joint likelihood can be optimized via a conditional variational auto-encoder and trained end-to-end on GPUs. Our MEDL_CVAE was motivated by two real-world applications in computational sustainability: one studies the spatial correlation among multiple bird species using the eBird data and the other models multi-dimensional landscape composition and human footprint in the Amazon rainforest with satellite images. We show that MEDL_CVAE captures rich dependency structures, scales better than previous methods, and further improves on the joint likelihood taking advantage of very large datasets that are beyond the capacity of previous methods.

In this paper, we tackle the vehicle Re-identification (ReID) problem which is of great importance in urban surveillance and can be used for multiple applications. In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed. With orientation invariant feature embedding, local region features of different orientations can be extracted based on 20 key point locations and can be well aligned and combined. With spatial-temporal regularization, the log-normal distribution is adopted to model the spatial-temporal constraints and the retrieval results can be refined. Experiments are conducted on public vehicle ReID datasets and our proposed method achieves state-of-the-art performance. Investigations of the proposed framework is conducted, including the landmark regressor and comparisons with attention mechanism. Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements.