Abstract:Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones. Hence, high quality and fast mapping becomes a fundamental problem. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, state-of-the-art (SOTA) works introduce GS to SLAM. Compared to classical pointcloud-SLAM, GS-SLAM generates photometric information by learning from input camera views and synthesize unseen views with high-quality textures. However, these GS-SLAM fail when moving objects occupy the scene that violate the static assumption of bundle adjustment. The failed updates of moving GS affects the static GS and contaminates the full map over long frames. Although some efforts have been made by concurrent works to consider moving objects for GS-SLAM, they simply detect and remove the moving regions from GS rendering ("anti'' dynamic GS-SLAM), where only the static background could benefit from GS. To this end, we propose the first real-time GS-SLAM, "DynaGSLAM'', that achieves high-quality online GS rendering, tracking, motion predictions of moving objects in dynamic scenes while jointly estimating accurate ego motion. Our DynaGSLAM outperforms SOTA static & "Anti'' dynamic GS-SLAM on three dynamic real datasets, while keeping speed and memory efficiency in practice.
Abstract:3D part segmentation is still an open problem in the field of 3D vision and AR/VR. Due to limited 3D labeled data, traditional supervised segmentation methods fall short in generalizing to unseen shapes and categories. Recently, the advancement in vision-language models' zero-shot abilities has brought a surge in open-world 3D segmentation methods. While these methods show promising results for 3D scenes or objects, they do not generalize well to 3D humans. In this paper, we present the first open-vocabulary segmentation method capable of handling 3D human. Our framework can segment the human category into desired fine-grained parts based on the textual prompt. We design a simple segmentation pipeline, leveraging SAM to generate multi-view proposals in 2D and proposing a novel HumanCLIP model to create unified embeddings for visual and textual inputs. Compared with existing pre-trained CLIP models, the HumanCLIP model yields more accurate embeddings for human-centric contents. We also design a simple-yet-effective MaskFusion module, which classifies and fuses multi-view features into 3D semantic masks without complex voting and grouping mechanisms. The design of decoupling mask proposals and text input also significantly boosts the efficiency of per-prompt inference. Experimental results on various 3D human datasets show that our method outperforms current state-of-the-art open-vocabulary 3D segmentation methods by a large margin. In addition, we show that our method can be directly applied to various 3D representations including meshes, point clouds, and 3D Gaussian Splatting.
Abstract:The reconstruction of 3D objects from calibrated photographs represents a fundamental yet intricate challenge in the domains of computer graphics and vision. Although neural reconstruction approaches based on Neural Radiance Fields (NeRF) have shown remarkable capabilities, their processing costs remain substantial. Recently, the advent of 3D Gaussian Splatting (3D-GS) largely improves the training efficiency and facilitates to generate realistic rendering in real-time. However, due to the limited ability of Spherical Harmonics (SH) to represent high-frequency information, 3D-GS falls short in reconstructing glossy objects. Researchers have turned to enhance the specular expressiveness of 3D-GS through inverse rendering. Yet these methods often struggle to maintain the training and rendering efficiency, undermining the benefits of Gaussian Splatting techniques. In this paper, we introduce GlossGau, an efficient inverse rendering framework that reconstructs scenes with glossy surfaces while maintaining training and rendering speeds comparable to vanilla 3D-GS. Specifically, we explicitly model the surface normals, Bidirectional Reflectance Distribution Function (BRDF) parameters, as well as incident lights and use Anisotropic Spherical Gaussian (ASG) to approximate the per-Gaussian Normal Distribution Function under the microfacet model. We utilize 2D Gaussian Splatting (2D-GS) as foundational primitives and apply regularization to significantly alleviate the normal estimation challenge encountered in related works. Experiments demonstrate that GlossGau achieves competitive or superior reconstruction on datasets with glossy surfaces. Compared with previous GS-based works that address the specular surface, our optimization time is considerably less.
Abstract:We identify two major limitations in the existing studies on retinal vessel segmentation: (1) Most existing works are restricted to one modality, i.e, the Color Fundus (CF). However, multi-modality retinal images are used every day in the study of retina and retinal diseases, and the study of vessel segmentation on the other modalities is scarce; (2) Even though a small amount of works extended their experiments to limited new modalities such as the Multi-Color Scanning Laser Ophthalmoscopy (MC), these works still require finetuning a separate model for the new modality. And the finetuning will require extra training data, which is difficult to acquire. In this work, we present a foundational universal vessel segmentation model (UVSM) for multi-modality retinal images. Not only do we perform the study on a much wider range of modalities, but also we propose a universal model to segment the vessels in all these commonly-used modalities. Despite being much more versatile comparing with existing methods, our universal model still demonstrates comparable performance with the state-of-the- art finetuned methods. To the best of our knowledge, this is the first work that achieves cross-modality retinal vessel segmentation and also the first work to study retinal vessel segmentation in some novel modalities.
Abstract:The compression of real-world scanned 3D human dynamic meshes is an emerging research area, driven by applications such as telepresence, virtual reality, and 3D digital streaming. Unlike synthesized dynamic meshes with fixed topology, scanned dynamic meshes often not only have varying topology across frames but also scan defects such as holes and outliers, increasing the complexity of prediction and compression. Additionally, human meshes often combine rigid and non-rigid motions, making accurate prediction and encoding significantly more difficult compared to objects that exhibit purely rigid motion. To address these challenges, we propose a compression method designed for real-world scanned human dynamic meshes, leveraging embedded key nodes. The temporal motion of each vertex is formulated as a distance-weighted combination of transformations from neighboring key nodes, requiring the transmission of solely the key nodes' transformations. To enhance the quality of the KeyNode-driven prediction, we introduce an octree-based residual coding scheme and a Dual-direction prediction mode, which uses I-frames from both directions. Extensive experiments demonstrate that our method achieves significant improvements over the state-of-the-art, with an average bitrate saving of 24.51% across the evaluated sequences, particularly excelling at low bitrates.
Abstract:A signed distance function (SDF) is a useful representation for continuous-space geometry and many related operations, including rendering, collision checking, and mesh generation. Hence, reconstructing SDF from image observations accurately and efficiently is a fundamental problem. Recently, neural implicit SDF (SDF-NeRF) techniques, trained using volumetric rendering, have gained a lot of attention. Compared to earlier truncated SDF (TSDF) fusion algorithms that rely on depth maps and voxelize continuous space, SDF-NeRF enables continuous-space SDF reconstruction with better geometric and photometric accuracy. However, the accuracy and convergence speed of scene-level SDF reconstruction require further improvements for many applications. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, several works have focused on improving SDF-NeRF by introducing consistency losses on depth and surface normals between 3DGS and SDF-NeRF. However, loss-level connections alone lead to incremental improvements. We propose a novel neural implicit SDF called "SplatSDF" to fuse 3DGSandSDF-NeRF at an architecture level with significant boosts to geometric and photometric accuracy and convergence speed. Our SplatSDF relies on 3DGS as input only during training, and keeps the same complexity and efficiency as the original SDF-NeRF during inference. Our method outperforms state-of-the-art SDF-NeRF models on geometric and photometric evaluation by the time of submission.
Abstract:Negation is a fundamental linguistic concept used by humans to convey information that they do not desire. Despite this, there has been minimal research specifically focused on negation within vision-language tasks. This lack of research means that vision-language models (VLMs) may struggle to understand negation, implying that they struggle to provide accurate results. One barrier to achieving human-level intelligence is the lack of a standard collection by which research into negation can be evaluated. This paper presents the first large-scale dataset, Negative Instruction (NeIn), for studying negation within the vision-language domain. Our dataset comprises 530,694 quadruples, i.e., source image, original caption, negative sentence, and target image in total, including 495,694 queries for training and 35,000 queries for benchmarking across multiple vision-language tasks. Specifically, we automatically generate NeIn based on a large, existing vision-language dataset, MS-COCO, via two steps: generation and filtering. During the generation phase, we leverage two VLMs, BLIP and MagicBrush, to generate the target image and a negative clause that expresses the content of the source image. In the subsequent filtering phase, we apply BLIP to remove erroneous samples. Additionally, we introduce an evaluation protocol for negation understanding of image editing models. Extensive experiments using our dataset across multiple VLMs for instruction-based image editing tasks demonstrate that even recent state-of-the-art VLMs struggle to understand negative queries. The project page is: https://tanbuinhat.github.io/NeIn/
Abstract:In this paper, we propose a deep learning based system for the task of deepfake audio detection. In particular, the draw input audio is first transformed into various spectrograms using three transformation methods of Short-time Fourier Transform (STFT), Constant-Q Transform (CQT), Wavelet Transform (WT) combined with different auditory-based filters of Mel, Gammatone, linear filters (LF), and discrete cosine transform (DCT). Given the spectrograms, we evaluate a wide range of classification models based on three deep learning approaches. The first approach is to train directly the spectrograms using our proposed baseline models of CNN-based model (CNN-baseline), RNN-based model (RNN-baseline), C-RNN model (C-RNN baseline). Meanwhile, the second approach is transfer learning from computer vision models such as ResNet-18, MobileNet-V3, EfficientNet-B0, DenseNet-121, SuffleNet-V2, Swint, Convnext-Tiny, GoogLeNet, MNASsnet, RegNet. In the third approach, we leverage the state-of-the-art audio pre-trained models of Whisper, Seamless, Speechbrain, and Pyannote to extract audio embeddings from the input spectrograms. Then, the audio embeddings are explored by a Multilayer perceptron (MLP) model to detect the fake or real audio samples. Finally, high-performance deep learning models from these approaches are fused to achieve the best performance. We evaluated our proposed models on ASVspoof 2019 benchmark dataset. Our best ensemble model achieved an Equal Error Rate (EER) of 0.03, which is highly competitive to top-performing systems in the ASVspoofing 2019 challenge. Experimental results also highlight the potential of selective spectrograms and deep learning approaches to enhance the task of audio deepfake detection.
Abstract:Facial action unit (AU) intensity plays a pivotal role in quantifying fine-grained expression behaviors, which is an effective condition for facial expression manipulation. However, publicly available datasets containing intensity annotations for multiple AUs remain severely limited, often featuring a restricted number of subjects. This limitation places challenges to the AU intensity manipulation in images due to disentanglement issues, leading researchers to resort to other large datasets with pretrained AU intensity estimators for pseudo labels. In addressing this constraint and fully leveraging manual annotations of AU intensities for precise manipulation, we introduce AUEditNet. Our proposed model achieves impressive intensity manipulation across 12 AUs, trained effectively with only 18 subjects. Utilizing a dual-branch architecture, our approach achieves comprehensive disentanglement of facial attributes and identity without necessitating additional loss functions or implementing with large batch sizes. This approach offers a potential solution to achieve desired facial attribute editing despite the dataset's limited subject count. Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool. AUEditNet allows conditioning by either intensity values or target images, eliminating the need for constructing AU combinations for specific facial expression synthesis. Moreover, AU intensity estimation, as a downstream task, validates the consistency between real and edited images, confirming the effectiveness of our proposed AU intensity manipulation method.
Abstract:Current monocular 3D scene reconstruction (3DR) works are either fully-supervised, or not generalizable, or implicit in 3D representation. We propose a novel framework - MonoSelfRecon that for the first time achieves explicit 3D mesh reconstruction for generalizable indoor scenes with monocular RGB views by purely self-supervision on voxel-SDF (signed distance function). MonoSelfRecon follows an Autoencoder-based architecture, decodes voxel-SDF and a generalizable Neural Radiance Field (NeRF), which is used to guide voxel-SDF in self-supervision. We propose novel self-supervised losses, which not only support pure self-supervision, but can be used together with supervised signals to further boost supervised training. Our experiments show that "MonoSelfRecon" trained in pure self-supervision outperforms current best self-supervised indoor depth estimation models and is comparable to 3DR models trained in fully supervision with depth annotations. MonoSelfRecon is not restricted by specific model design, which can be used to any models with voxel-SDF for purely self-supervised manner.