Temporally Consistent Stereo Matching

Stereo matching provides depth estimation from binocular images for downstream applications. These applications mostly take video streams as input and require temporally consistent depth maps. However, existing methods mainly focus on the estimation at the single-frame level. This commonly leads to temporally inconsistent results, especially in ill-posed regions. In this paper, we aim to leverage temporal information to improve the temporal consistency, accuracy, and efficiency of stereo matching. To achieve this, we formulate video stereo matching as a process of temporal disparity completion followed by continuous iterative refinements. Specifically, we first project the disparity of the previous timestamp to the current viewpoint, obtaining a semi-dense disparity map. Then, we complete this map through a disparity completion module to obtain a well-initialized disparity map. The state features from the current completion module and from the past refinement are fused together, providing a temporally coherent state for subsequent refinement. Based on this coherent state, we introduce a dual-space refinement module to iteratively refine the initialized result in both disparity and disparity gradient spaces, improving estimations in ill-posed regions. Extensive experiments demonstrate that our method effectively alleviates temporal inconsistency while enhancing both accuracy and efficiency.

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

Fine-Grained Annotation for Face Anti-Spoofing

Face anti-spoofing plays a critical role in safeguarding facial recognition systems against presentation attacks. While existing deep learning methods show promising results, they still suffer from the lack of fine-grained annotations, which lead models to learn task-irrelevant or unfaithful features. In this paper, we propose a fine-grained annotation method for face anti-spoofing. Specifically, we first leverage the Segment Anything Model (SAM) to obtain pixel-wise segmentation masks by utilizing face landmarks as point prompts. The face landmarks provide segmentation semantics, which segments the face into regions. We then adopt these regions as masks and assemble them into three separate annotation maps: spoof, living, and background maps. Finally, we combine three separate maps into a three-channel map as annotations for model training. Furthermore, we introduce the Multi-Channel Region Exchange Augmentation (MCREA) to diversify training data and reduce overfitting. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches in both intra-dataset and cross-dataset evaluations.

Neural 3D Scene Reconstruction from Multiple 2D Images without 3D Supervision

Neural 3D scene reconstruction methods have achieved impressive performance when reconstructing complex geometry and low-textured regions in indoor scenes. However, these methods heavily rely on 3D data which is costly and time-consuming to obtain in real world. In this paper, we propose a novel neural reconstruction method that reconstructs scenes using sparse depth under the plane constraints without 3D supervision. We introduce a signed distance function field, a color field, and a probability field to represent a scene. We optimize these fields to reconstruct the scene by using differentiable ray marching with accessible 2D images as supervision. We improve the reconstruction quality of complex geometry scene regions with sparse depth obtained by using the geometric constraints. The geometric constraints project 3D points on the surface to similar-looking regions with similar features in different 2D images. We impose the plane constraints to make large planes parallel or vertical to the indoor floor. Both two constraints help reconstruct accurate and smooth geometry structures of the scene. Without 3D supervision, our method achieves competitive performance compared with existing methods that use 3D supervision on the ScanNet dataset.

Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding

Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length. General efficient transformers are challenging to be directly adapted to model document. They are unable to handle the layout representation in documents, e.g. word, line and paragraph, on different granularity levels and seem hard to achieve a good trade-off between efficiency and performance. To tackle the concerns, we propose Fast-StrucTexT, an efficient multi-modal framework based on the StrucTexT algorithm with an hourglass transformer architecture, for visual document understanding. Specifically, we design a modality-guided dynamic token merging block to make the model learn multi-granularity representation and prunes redundant tokens. Additionally, we present a multi-modal interaction module called Symmetry Cross Attention (SCA) to consider multi-modal fusion and efficiently guide the token mergence. The SCA allows one modality input as query to calculate cross attention with another modality in a dual phase. Extensive experiments on FUNSD, SROIE, and CORD datasets demonstrate that our model achieves the state-of-the-art performance and almost 1.9X faster inference time than the state-of-the-art methods.

Exploring Data Geometry for Continual Learning

Continual learning aims to efficiently learn from a non-stationary stream of data while avoiding forgetting the knowledge of old data. In many practical applications, data complies with non-Euclidean geometry. As such, the commonly used Euclidean space cannot gracefully capture non-Euclidean geometric structures of data, leading to inferior results. In this paper, we study continual learning from a novel perspective by exploring data geometry for the non-stationary stream of data. Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and prevents forgetting by keeping geometric structures of old data into account. In doing so, making use of the mixed curvature space, we propose an incremental search scheme, through which the growing geometric structures are encoded. Then, we introduce an angular-regularization loss and a neighbor-robustness loss to train the model, capable of penalizing the change of global geometric structures and local geometric structures. Experiments show that our method achieves better performance than baseline methods designed in Euclidean space.

A Decomposition Model for Stereo Matching

In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of stereo matching at the original resolution, our model only runs dense matching at a very low resolution and uses sparse matching at different higher resolutions to recover the disparity of lost details scale-by-scale. After the decomposition of stereo matching, our model iteratively fuses the sparse and dense disparity maps from adjacent scales with an occlusion-aware mask. A refinement network is also applied to improving the fusion result. Compared with high-performance methods like PSMNet and GANet, our method achieves $10-100\times$ speed increase while obtaining comparable disparity estimation results.

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds, which is inferior because tangent space is only a local approximation of a manifold. In this paper, we propose a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that directly works on hyperbolic manifolds. Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation. The hyperbolic feature transformation works as linear transformation on hyperbolic manifolds. It ensures the transformed node representations still lie on the hyperbolic manifold by imposing the orthogonal constraint on the transformation sub-matrix. The hyperbolic neighborhood aggregation updates each node representation via the Einstein midpoint. The H2H-GCN avoids the distortion caused by tangent space approximations and keeps the global hyperbolic structure. Extensive experiments show that the H2H-GCN achieves substantial improvements on the link prediction, node classification, and graph classification tasks.

Video Captioning Using Weak Annotation

Video captioning has shown impressive progress in recent years. One key reason of the performance improvements made by existing methods lie in massive paired video-sentence data, but collecting such strong annotation, i.e., high-quality sentences, is time-consuming and laborious. It is the fact that there now exist an amazing number of videos with weak annotation that only contains semantic concepts such as actions and objects. In this paper, we investigate using weak annotation instead of strong annotation to train a video captioning model. To this end, we propose a progressive visual reasoning method that progressively generates fine sentences from weak annotations by inferring more semantic concepts and their dependency relationships for video captioning. To model concept relationships, we use dependency trees that are spanned by exploiting external knowledge from large sentence corpora. Through traversing the dependency trees, the sentences are generated to train the captioning model. Accordingly, we develop an iterative refinement algorithm that refines sentences via spanning dependency trees and fine-tunes the captioning model using the refined sentences in an alternative training manner. Experimental results demonstrate that our method using weak annotation is very competitive to the state-of-the-art methods using strong annotation.

Content-Aware Inter-Scale Cost Aggregation for Stereo Matching

Cost aggregation is a key component of stereo matching for high-quality depth estimation. Most methods use multi-scale processing to downsample cost volume for proper context information, but will cause loss of details when upsampling. In this paper, we present a content-aware inter-scale cost aggregation method that adaptively aggregates and upsamples the cost volume from coarse-scale to fine-scale by learning dynamic filter weights according to the content of the left and right views on the two scales. Our method achieves reliable detail recovery when upsampling through the aggregation of information across different scales. Furthermore, a novel decomposition strategy is proposed to efficiently construct the 3D filter weights and aggregate the 3D cost volume, which greatly reduces the computation cost. We first learn the 2D similarities via the feature maps on the two scales, and then build the 3D filter weights based on the 2D similarities from the left and right views. After that, we split the aggregation in a full 3D spatial-disparity space into the aggregation in 1D disparity space and 2D spatial space. Experiment results on Scene Flow dataset, KITTI2015 and Middlebury demonstrate the effectiveness of our method.