NeurIPS 2024 Papers

Visual text generation has significantly advanced through diffusion models aimed at producing images with readable and realistic text. Recent works primarily use a ControlNet-based framework, employing standard font text images to control diffusion models. Recognizing the critical role of control information in generating high-quality text, we investigate its influence from three perspectives: input encoding, role at different stages, and output features. Our findings reveal that: 1) Input control information has unique characteristics compared to conventional inputs like Canny edges and depth maps. 2) Control information plays distinct roles at different stages of the denoising process. 3) Output control features significantly differ from the base and skip features of the U-Net decoder in the frequency domain. Based on these insights, we propose TextGen, a novel framework designed to enhance generation quality by optimizing control information. We improve input and output features using Fourier analysis to emphasize relevant information and reduce noise. Additionally, we employ a two-stage generation framework to align the different roles of control information at different stages. Furthermore, we introduce an effective and lightweight dataset for training. Our method achieves state-of-the-art performance in both Chinese and English text generation. The code and dataset are available at https://github.com/CyrilSterling/TextGen.

Synthesizing time series data is pivotal in modern society, aiding effective decision making and ensuring privacy preservation in various scenarios. Time series are associated with various attributes, including trends, seasonality, and external information such as location. Recent research has predominantly focused on random unconditional synthesis or conditional synthesis. Nonetheless, these paradigms generate time series from scratch and are incapable of manipulating existing time series samples. This paper introduces a novel task, called Time Series Editing (TSE), to synthesize time series by manipulating existing time series. The objective is to modify the given time series according to the specified attributes while preserving other properties unchanged. This task is not trivial due to the inadequacy of data coverage and the intricate relationships between time series and their attributes. To address these issues, we introduce a novel diffusion model, called TEdit. The proposed TEdit is trained using a novel bootstrap learning algorithm that effectively enhances the coverage of the original data. It is also equipped with an innovative multi-resolution modeling and generation paradigm to capture the complex relationships between time series and their attributes. Experimental results demonstrate the efficacy of TEdit for editing specified attributes upon the existing time series data. The project page is at https://seqml.github.io/tse.

Recent advancements in vision-language-to-image (VL2I) diffusion generation have made significant progress. While generating images from broad vision-language inputs holds promise, it also raises concerns about potential misuse, such as copying artistic styles without permission, which could have legal and social consequences. Therefore, it's crucial to establish governance frameworks to ensure ethical and copyright integrity, especially with widely used diffusion models. To address these issues, researchers have explored various approaches, such as dataset filtering, adversarial perturbations, machine unlearning, and inference-time refusals. However, these methods often lack either scalability or effectiveness. In response, we propose a new framework called causal representation editing (CRE), which extends representation editing from large language models (LLMs) to diffusion-based models. CRE enhances the efficiency and flexibility of safe content generation by intervening at diffusion timesteps causally linked to unsafe concepts. This allows for precise removal of harmful content while preserving acceptable content quality, demonstrating superior effectiveness, precision and scalability compared to existing methods. CRE can handle complex scenarios, including incomplete or blurred representations of unsafe concepts, offering a promising solution to challenges in managing harmful content generation in diffusion-based models.

Flexible and accurate drag-based editing is a challenging task that has recently garnered significant attention. Current methods typically model this problem as automatically learning "how to drag" through point dragging and often produce one deterministic estimation, which presents two key limitations: 1) Overlooking the inherently ill-posed nature of drag-based editing, where multiple results may correspond to a given input, as illustrated in Fig.1; 2) Ignoring the constraint of image quality, which may lead to unexpected distortion. To alleviate this, we propose LucidDrag, which shifts the focus from "how to drag" to "what-then-how" paradigm. LucidDrag comprises an intention reasoner and a collaborative guidance sampling mechanism. The former infers several optimal editing strategies, identifying what content and what semantic direction to be edited. Based on the former, the latter addresses "how to drag" by collaboratively integrating existing editing guidance with the newly proposed semantic guidance and quality guidance. Specifically, semantic guidance is derived by establishing a semantic editing direction based on reasoned intentions, while quality guidance is achieved through classifier guidance using an image fidelity discriminator. Both qualitative and quantitative comparisons demonstrate the superiority of LucidDrag over previous methods.

The notion of algorithmic fairness has been actively explored from various aspects of fairness, such as counterfactual fairness (CF) and group fairness (GF). However, the exact relationship between CF and GF remains to be unclear, especially in image classification tasks; the reason is because we often cannot collect counterfactual samples regarding a sensitive attribute, essential for evaluating CF, from the existing images (e.g., a photo of the same person but with different secondary sex characteristics). In this paper, we construct new image datasets for evaluating CF by using a high-quality image editing method and carefully labeling with human annotators. Our datasets, CelebA-CF and LFW-CF, build upon the popular image GF benchmarks; hence, we can evaluate CF and GF simultaneously. We empirically observe that CF does not imply GF in image classification, whereas previous studies on tabular datasets observed the opposite. We theoretically show that it could be due to the existence of a latent attribute $G$ that is correlated with, but not caused by, the sensitive attribute (e.g., secondary sex characteristics are highly correlated with hair length). From this observation, we propose a simple baseline, Counterfactual Knowledge Distillation (CKD), to mitigate such correlation with the sensitive attributes. Extensive experimental results on CelebA-CF and LFW-CF demonstrate that CF-achieving models satisfy GF if we successfully reduce the reliance on $G$ (e.g., using CKD).

Recent advancements in models linking natural language with human motions have shown significant promise in motion generation and editing based on instructional text. Motivated by applications in sports coaching and motor skill learning, we investigate the inverse problem: generating corrective instructional text, leveraging motion editing and generation models. We introduce a novel approach that, given a user’s current motion (source) and the desired motion (target), generates text instructions to guide the user towards achieving the target motion. We leverage large language models to generate corrective texts and utilize existing motion generation and editing frameworks to compile datasets of triplets (source motion, target motion, and corrective text). Using this data, we propose a new motion-language model for generating corrective instructions. We present both qualitative and quantitative results across a diverse range of applications that largely improve upon baselines. Our approach demonstrates its effectiveness in instructional scenarios, offering text-based guidance to correct and enhance user performance.

Editing biological sequences has extensive applications in synthetic biology and medicine, such as designing regulatory elements for nucleic-acid therapeutics and treating genetic disorders. The primary objective in biological-sequence editing is to determine the optimal modifications to a sequence which augment certain biological properties while adhering to a minimal number of alterations to ensure predictability and potentially support safety. In this paper, we propose GFNSeqEditor, a novel biological-sequence editing algorithm which builds on the recently proposed area of generative flow networks (GFlowNets). Our proposed GFNSeqEditor identifies elements within a starting seed sequence that may compromise a desired biological property. Then, using a learned stochastic policy, the algorithm makes edits at these identified locations, offering diverse modifications for each sequence to enhance the desired property. The number of edits can be regulated through specific hyperparameters. We conducted extensive experiments on a range of real-world datasets and biological applications, and our results underscore the superior performance of our proposed algorithm compared to existing state-of-the-art sequence editing methods.

The commercial text-to-image deep generation models (e.g. DALL·E) can produce high-quality images based on input language descriptions. These models incorporate a black-box safety filter to prevent the generation of unsafe or unethical content, such as violent, criminal, or hateful imagery. Recent jailbreaking methods generate adversarial prompts capable of bypassing safety filters and producing unsafe content, exposing vulnerabilities in influential commercial models. However, once these adversarial prompts are identified, the safety filter can be updated to prevent the generation of unsafe images. In this work, we propose an effective, simple, and difficult-to-detect jailbreaking solution: generating safe content initially with normal text prompts and then editing the generations to embed unsafe content. The intuition behind this idea is that the deep generation model cannot reject safe generation with normal text prompts, while the editing models focus on modifying the local regions of images and do not involve a safety strategy. However, implementing such a solution is non-trivial, and we need to overcome several challenges: how to automatically confirm the normal prompt to replace the unsafe prompts, and how to effectively perform editable replacement and naturally generate unsafe content. In this work, we propose the collaborative generation and editing for jailbreaking text-to-image deep generation (ColJailBreak), which comprises three key components: adaptive normal safe substitution, inpainting-driven injection of unsafe content, and contrastive language-image-guided collaborative optimization. We validate our method on three datasets and compare it to two baseline methods. Our method could generate unsafe content through two commercial deep generation models including GPT-4 and DALL·E 2.

We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, *Neural Assets*, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from the target frame, which enables learning disentangled appearance and position features. Combining visual and 3D pose representations in a sequence-of-tokens format allows us to keep the text-to-image interface of existing models, with Neural Assets in place of text tokens. By fine-tuning a pre-trained text-to-image diffusion model with this information, our approach enables fine-grained 3D pose and placement control of individual objects in a scene. We further demonstrate that Neural Assets can be transferred and recomposed across different scenes. Our model achieves state-of-the-art multi-object editing results on both synthetic 3D scene datasets, as well as two real-world video datasets (Objectron, Waymo Open).

Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in computer graphics, faces unique challenges. A major challenge is making simultaneous edits across multiple objects or attributes. Applying these methods sequentially for multi-attribute edits increases computational demands and efficiency losses. In this paper, we address these challenges with significant contributions. Our main contribution is the development of ParallelEdits, a method that seamlessly manages simultaneous edits across multiple attributes. In contrast to previous approaches, ParallelEdits not only preserves the quality of single attribute edits but also significantly improves the performance of multitasking edits. This is achieved through innovative attention distribution mechanism and multi-branch design that operates across several processing heads. Additionally, we introduce the PIE-Bench++ dataset, an expansion of the original PIE-Bench dataset, to better support evaluating image-editing tasks involving multiple objects and attributes simultaneously. This dataset is a benchmark for evaluating text-driven image editing methods in multifaceted scenarios.

Images contain objects with deformable boundaries, such as the contours of a human face, yet attention operators act on square windows. This mixes features from perceptually unrelated regions, which can degrade the quality of a denoiser. One can exclude pixels using an estimate of perceptual groupings, such as superpixels, but the naive use of superpixels can be theoretically and empirically worse than standard attention. Using superpixel probabilities rather than superpixel assignments, this paper proposes soft superpixel neighborhood attention (SNA), which interpolates between the existing neighborhood attention and the naive superpixel neighborhood attention. This paper presents theoretical results showing SNA is the optimal denoiser under a latent superpixel model. SNA outperforms alternative local attention modules on image denoising, and we compare the superpixels learned from denoising with those learned with supervision.

We propose a video editing framework, NaRCan, which integrates a hybrid deformation field and diffusion prior to generate high-quality natural canonical images to represent the input video. Our approach utilizes homography to model global motion and employs multi-layer perceptrons (MLPs) to capture local residual deformations, enhancing the model’s ability to handle complex video dynamics. By introducing a diffusion prior from the early stages of training, our model ensures that the generated images retain a high-quality natural appearance, making the produced canonical images suitable for various downstream tasks in video editing, a capability not achieved by current canonical-based methods. Furthermore, we incorporate low-rank adaptation (LoRA) fine-tuning and introduce a noise and diffusion prior update scheduling technique that accelerates the training process by 14 times. Extensive experimental results show that our method outperforms existing approaches in various video editing tasks and produces coherent and high-quality edited video sequences. See our project page for video results: [koi953215.github.io/NaRCan_page](https://koi953215.github.io/NaRCan_page/).

Diffusion distillation represents a highly promising direction for achieving faithful text-to-image generation in a few sampling steps. However, despite recent successes, existing distilled models still do not provide the full spectrum of diffusion abilities, such as real image inversion, which enables many precise image manipulation methods. This work aims to enrich distilled text-to-image diffusion models with the ability to effectively encode real images into their latent space. To this end, we introduce invertible Consistency Distillation (iCD), a generalized consistency distillation framework that facilitates both high-quality image synthesis and accurate image encoding in only 3-4 inference steps. Though the inversion problem for text-to-image diffusion models gets exacerbated by high classifier-free guidance scales, we notice that dynamic guidance significantly reduces reconstruction errors without noticeable degradation in generation performance. As a result, we demonstrate that iCD equipped with dynamic guidance may serve as a highly effective tool for zero-shot text-guided image editing, competing with more expensive state-of-the-art alternatives.

Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. These errors accumulate during the diffusion process, resulting in inferior content preservation and edit fidelity, especially with conditional inputs. We address these challenges by investigating the primary contributors to error accumulation in DDIM inversion and identify the singularity problem in traditional noise schedules as a key issue. To resolve this, we introduce the *Logistic Schedule*, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. This schedule reduces noise prediction errors, enabling more faithful editing that preserves the original content of the source image. Our approach requires no additional retraining and is compatible with various existing editing methods. Experiments across eight editing tasks demonstrate the Logistic Schedule's superior performance in content preservation and edit fidelity compared to traditional noise schedules, highlighting its adaptability and effectiveness. The project page is available at https://lonelvino.github.io/SYE/.

Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements. However, these works mainly focus on confined categories or synthetic 3D assets, which are discouraged from generalizing to challenging in-the-wild scenes and fail to be employed with 2D synthesis directly. Moreover, these methods heavily depended on camera poses, limiting their real-world applications. To overcome these issues, we propose MVInpainter, re-formulating the 3D editing as a multi-view 2D inpainting task. Specifically, MVInpainter partially inpaints multi-view images with the reference guidance rather than intractably generating an entirely novel view from scratch, which largely simplifies the difficulty of in-the-wild NVS and leverages unmasked clues instead of explicit pose conditions. To ensure cross-view consistency, MVInpainter is enhanced by video priors from motion components and appearance guidance from concatenated reference key\&value attention. Furthermore, MVInpainter incorporates slot attention to aggregate high-level optical flow features from unmasked regions to control the camera movement with pose-free training and inference. Sufficient scene-level experiments on both object-centric and forward-facing datasets verify the effectiveness of MVInpainter, including diverse tasks, such as multi-view object removal, synthesis, insertion, and replacement. The project page is https://ewrfcas.github.io/MVInpainter/.

Recent text-to-image (T2I) personalization methods have shown great premise in teaching a diffusion model user-specified concepts given a few images for reusing the acquired concepts in a novel context. With massive efforts being dedicated to personalized generation, a promising extension is personalized editing, namely to edit an image using personalized concepts, which can provide more precise guidance signal than traditional textual guidance. To address this, one straightforward solution is to incorporate a personalized diffusion model with a text-driven editing framework. However, such solution often shows unsatisfactory editability on the source image. To address this, we propose DreamSteerer, a plug-in method for augmenting existing T2I personalization methods. Specifically, we enhance the source image conditioned editability of a personalized diffusion model via a novel Editability Driven Score Distillation (EDSD) objective. Moreover, we identify a mode trapping issue with EDSD, and propose a mode shifting regularization with spatial feature guided sampling to avoid such issue. We further employ two key modifications on the Delta Denoising Score framework that enable high-fidelity local editing with personalized concepts. Extensive experiments validate that DreamSteerer can significantly improve the editability of several T2I personalization baselines while being computationally efficient.

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing LVLM editing benchmark, which comprises three metrics (Reliability, Locality, and Generality), falls short in the quality of synthesized evaluation images and cannot assess whether models apply edited knowledge in relevant content. Therefore, we employ more reliable data collection methods to construct a new Large $\textbf{V}$ision-$\textbf{L}$anguage Model $\textbf{K}$nowledge $\textbf{E}$diting $\textbf{B}$enchmark, $\textbf{VLKEB}$, and extend the Portability metric for more comprehensive evaluation. Leveraging a multi-modal knowledge graph, our image data are bound with knowledge entities. This can be further used to extract entity-related knowledge, which constitutes the base of editing data. We conduct experiments of different editing methods on five LVLMs, and thoroughly analyze how do they impact the models. The results reveal strengths and deficiencies of these methods and hopefully provide insights for future research. The codes and dataset are available at: https://github.com/VLKEB/VLKEB.

Despite satisfactory results on ``easy'' cases of single image reflection separation, prior dual-stream methods still suffer from considerable performance degradation when facing complex ones, i.e, the transmission layer is densely entangled with the reflection having a wide distribution of spatial intensity. The main reasons come from the lack of concern on the feature correlation during interaction, and the limited receptive field. To remedy these deficiencies, this paper presents a Dual-Stream Interactive Transformer (DSIT) design. Specifically, we devise a dual-attention interactive structure that embraces a dual-stream self-attention and a layer-aware dual-stream cross-attention mechanism to simultaneously capture intra-layer and inter-layer feature correlations. Meanwhile, the introduction of attention mechanisms can also mitigate the receptive field limitation. We modulate single-stream pre-trained Transformer embeddings with dual-stream convolutional features through cross-architecture interactions to provide richer semantic priors, thereby further relieving the ill-posedness of the problem. Extensive experimental results reveal the merits of the proposed DSIT over other state-of-the-art alternatives. Our code is publicly available at https://github.com/mingcv/DSIT.