Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting

• URL: http://arxiv.org/abs/2604.16747v1
• Date: Fri, 17 Apr 2026 23:41:50 GMT
• Title: Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting
• Abstract summary: Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but poorly on D-NeRF benchmark.<n>We measure an average train-test PSNR gap of 6.18 dB, rising to 11 dB on individual scenes.<n>We show that the capacity explanation is incomplete. Elastic Energy Regularization (EER) reduces the gap by 40.8% while growing the cloud by 85%.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but generalize poorly: on the D-NeRF benchmark we measure an average train-test PSNR gap of 6.18 dB, rising to 11 dB on individual scenes. We report two findings that together account for most of that gap. Finding 1 (the role of splitting). A systematic ablation of the Adaptive Density Control pipeline (split, clone, prune, frequency, threshold, schedule) shows that splitting is responsible for over 80% of the gap: disabling split collapses the cloud from 44K to 3K Gaussians and the gap from 6.18 dB to 1.15 dB. Across all threshold-varying ablations, gap is log-linear in count (r = 0.995, bootstrap 95% CI [0.99, 1.00]), which suggests a capacity-based explanation. Finding 2 (the role of deformation coherence). We show that the capacity explanation is incomplete. A local-smoothness penalty on the per-Gaussian deformation field -- Elastic Energy Regularization (EER) -- reduces the gap by 40.8% while growing the cloud by 85%. Measuring per-Gaussian strain directly on trained checkpoints, EER reduces mean strain by 99.72% (median 99.80%) across all 8 scenes; on 8/8 scenes the median Gaussian under EER is less strained than the 1st-percentile (best-behaved) Gaussian under baseline. Alongside EER, we evaluate two further regularizers: GAD, a loss-rate-aware densification threshold, and PTDrop, a jitter-weighted Gaussian dropout. GAD+EER reduces the gap by 48%; adding PTDrop and a soft growth cap reaches 57%. We confirm that coherence generalizes to (a) a different deformation architecture (Deformable-3DGS, +40.6% gap reduction at re-tuned lambda), and (b) real monocular video (4 HyperNeRF scenes, reducing the mean PSNR gap by 14.9% at the same lambda as D-NeRF, with near-zero quality cost). The overfitting in dynamic 3DGS is driven by incoherent deformation, not parameter count.

Related papers

• Conditioning noise is a free regularizer for LoRA fine-tuning: no pathology encoder required for diffusion-based artifact detection in histopathology [1.8864137667201766]
  Diffusion-based artifact detectors score whole-slide image patches by reconstruction error under a model fine-tuned on clean tissue.<n>We show that conditioning this fine-tuning on random Gaussian embeddings consistently widens the clean/artifact separation.
  arXiv  Detail & Related papers  (2026-09-11T07:16:38Z)
• SPARC-Net: A Spectral, Causality-Aware, and Hard-Constrained Physics-Informed Architecture for Stiff and Shock-Dominated Partial Differential Equations [0.0654051537828115]
  Physics-Informed Neural Networks (PINNs) provide a meshless approach for solving partial differential equations (PDEs)<n>PINNs suffer severe degradation in stiff and shock-dominated problems, where small PDE residuals can correspond to globally inaccurate solutions.<n>We show these failures are multi-causal, arising from the concurrent interplay of (i) spectral bias against sharp features, (ii) imbalanced multi-term optimization and loss-weight collapse, (iii) violation of temporal causality, and (iv) under-resolved collocation.<n>We present-Net, a unified architecture and training
  arXiv  Detail & Related papers  (2026-07-13T09:23:17Z)
• The Gentle Collapse: Distributional Metrics for Continual Learning [7.30570760963699]
  We introduce six softmax-derived metrics spanning true-label rank (TLR), predictive confidence, and distributional divergence that characterize forgetting continuously.<n>On CIFAR-100, these metrics carry information where accuracy does not: at 0% accuracy, the Confusion Margin spans an IQR of [0.32, 0.50] across classes that accuracy treats identically.<n>Per-sample metric scores used as loss weights reduce forgetting by 1.3 percentage points over uniform experience replay (ER) on CIFAR-100.
  arXiv  Detail & Related papers  (2026-06-23T20:53:06Z)
• PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation [17.919178151901573]
  We show that standard on-policy distillation (OPD) for large language models suffers from severe training pathologies in practice.<n>PowerOPD is a sign-consistent reward from the Box-Cox power transformation, parameterized by alpha > 0, of which the log-ratio is the degenerate alpha -> 0 limit.<n>It achieves benchmark-averaged Avg@8/Pass@8 gains of up to +6.37/+5.71 over vanilla OPD, +3.01/+3.54 over post-hoc stabilization, and +2.59/+8.90 over full-vocabulary OPD.
  arXiv  Detail & Related papers  (2026-06-15T18:37:51Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Normalized Architectures are Natively 4-Bit [49.13186675123547]
  nGPT, an architecture that constrains weights and hidden representations to the unit hypersphere, is inherently more robust to low-precision arithmetic.<n>We validate this approach on both a 1.2B dense model and hybrid (Mamba-Transformer) MoE models of up to 3B/30B parameters.
  arXiv  Detail & Related papers  (2026-05-07T11:54:07Z)
• Visual Implicit Autoregressive Modeling [42.343328817507505]
  We introduce Visual Implicit Autoregressive Modeling (VIAR), a next-scale autoregressive generator that embeds an implicit equilibrium layer between shallow pre/post blocks.<n>VIAR attains FID 2.16, and sFID 8.07 on the ImageNet 256x256 benchmark.<n>By controlling the per-scale knob, VIAR can reduce peak memory from 19.24 GB to 8.53 GB and doubles throughput.
  arXiv  Detail & Related papers  (2026-05-02T03:23:17Z)
• Quantization Dominates Rank Reduction for KV-Cache Compression [0.0]
  quantization consistently outperforms rank reduction by 4-364 PPL depending on model and compression level.<n>We formalize this via a result showing projection damage exceeds quantization damage by 3 x 2 (2b) per direction under the softmax Fisher metric.
  arXiv  Detail & Related papers  (2026-04-13T14:06:18Z)
• When Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems [0.6875312133832079]
  Generative models are widely used to compensate for class imbalance in AI training pipelines.<n>FastGAN augmentation does not merely underperform at very low training set sizes but actively increases bias.<n> Stable Diffusion with Low-Rank Adaptation produced the best results overall.
  arXiv  Detail & Related papers  (2026-03-17T05:37:17Z)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Potential-energy gating for robust state estimation in bistable stochastic systems [0.0]
  We introduce potential-energy gating, a method for robust state estimation in systems governed by double-well dynamics.<n>We implement gating within Extended, Unscented, Ensemble, and Adaptive Kalman filters and particle filters.
  arXiv  Detail & Related papers  (2026-02-12T08:43:34Z)
• Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization [6.908972852063454]
  Temporal action localization requires both precise boundary detection and computational efficiency.<n>We address this through two complementary innovations: Boundary Distance Regression (BDR) and Adaptive Temporal Refinement (ATR)<n>On THUMOS14, our method achieves 56.5% mAP@0.7 with 151G FLOPs, using 36% fewer FLOPs than ActionFormer++ (55.7% mAP@0.7 at 235G)
  arXiv  Detail & Related papers  (2025-11-06T00:41:54Z)
• Ensemble Threshold Calibration for Stable Sensitivity Control [0.0]
  We present an end-to-end framework that achieves exact recall with sub-percent variance over tens of millions of geometry pairs.<n>Our approach consistently hits a recall target within a small error, decreases redundant verifications relative to other calibrations, and runs end-to-end on a single TPU v3 core.
  arXiv  Detail & Related papers  (2025-10-02T15:22:28Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• On the Training Instability of Shuffling SGD with Batch Normalization [44.28777474091466]
  Single Shuffle (SS) and Random Reshuffle (RR) interact surprisingly differently in the presence of batch normalization. We show that SS leads to distorted optima in regression and divergence for classification, whereas RR avoids both distortion and divergence.
  arXiv  Detail & Related papers  (2023-02-24T04:10:54Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• PENNI: Pruned Kernel Sharing for Efficient CNN Inference [41.050335599000036]
  State-of-the-art (SOTA) CNNs achieve outstanding performance on various tasks. Their high computation demand and massive number of parameters make it difficult to deploy these SOTA CNNs onto resource-constrained devices. We propose PENNI, a CNN model compression framework that is able to achieve model compactness and hardware efficiency simultaneously.
  arXiv  Detail & Related papers  (2020-05-14T16:57:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.